© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 211529
    Prev
    Next
    INDEX
    Explanations

    questions and discussions

    np_acts-logits-general · gemini-2.5-flash-lite

    General Kenobi and reasoning problems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Prepare
    0.44
    倾向
    0.41
    เ
    0.41
    一种
    0.41
    不起
    0.40
    Selecting
    0.40
     saison
    0.40
    就是
    0.39
    嘶
    0.39
    iz
    0.39
    POSITIVE LOGITS
    갖
    0.47
    YLE
    0.46
     needful
    0.44
     mainstream
    0.44
     pertinentes
    0.43
    тына
    0.43
     nécessaires
    0.43
     productive
    0.42
    Ы
    0.42
    ᱘
    0.41
    Activations Density 0.000%

    No Known Activations